Upload folder using huggingface_hub

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+tags:
+- pytorch
+- image-classification
+- robust-representation
+- modular-ai
+- dynamic-masking
+- dinov2
+- ifam
+arxiv: 2506.08915
+library_name: generic
+---
+
+# iFAM (imagenet-k1) Model Checkpoint
+
+This is the official pre-trained checkpoint of the **iFAM (Inherently Faithful Attention Maps for Vision Transformers)** framework, proposed in the paper **"Two-stage Vision Transformers and Hard Masking offer Robust Object Representations"** (accepted as an oral presentation at ICPR 2026).
+
+- **Paper:** [Two-stage Vision Transformers and Hard Masking offer Robust Object Representations](https://arxiv.org/abs/2506.08915)
+- **Repository:** [GitHub - ananthu-aniraj/ifam](https://github.com/ananthu-aniraj/ifam)
+
+## Model Description
+iFAM model trained on the ImageNet-1K dataset with 1 part (K=1).
+
+The iFAM framework is a two-stage approach:
+1. **Stage 1 (Selector):** Processes the full image to discover object parts and identify task-relevant regions.
+2. **Stage 2 (Predictor):** Restricts its receptive field to the selected regions using input attention masking, preventing spurious background details from affecting the classification.
+
+## Usage
+
+To use this model, ensure you have the `ifam` repository cloned and the dependencies installed. You can load this model directly from the Hugging Face Hub:
+
+```python
+import torch
+import sys
+# Append the path to the ifam repository
+sys.path.append("/path/to/ifam")
+
+from models import FullTwoStageModelDoubleClassify
+
+# Load the model directly from Hugging Face Hub
+model = FullTwoStageModelDoubleClassify.from_pretrained("ananthu-aniraj/ifam-imagenet-k1")
+model.eval()
+
+# Example: Run inference
+# x = torch.rand(1, 3, 224, 224)
+# with torch.no_grad():
+#     outputs = model(x)
+```
+
+## Citation
+If you use this model in your research, please cite:
+```bibtex
+@inproceedings{aniraj2026ifam,
+  title={Two-stage Vision Transformers and Hard Masking offer Robust Object Representations},
+  author={Aniraj, Ananthu and Dantas, Cassio F. and Ienco, Dino and Marcos, Diego},
+  booktitle={International Conference on Pattern Recognition (ICPR)},
+  year={2026}
+}
+```

config.json

@@ -0,0 +1,15 @@
+{
+  "gumbel_softmax": true,
+  "img_size": 224,
+  "init_model_stage_1": null,
+  "init_model_stage_2": null,
+  "model_arch": "vit_base_patch14_reg4_dinov2.lvd142m",
+  "num_classes": 1000,
+  "num_landmarks": 1,
+  "part_dropout": 0.3,
+  "part_dropout_stage_2": 0.3,
+  "part_logits_threshold": null,
+  "return_transformer_qkv": false,
+  "softmax_temperature": 1.0,
+  "use_soft_masks": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:775cb2d703bd93db1a29488b6a6bae855d62c0b19b9f054f1511ed9675d71d51
+size 692022348